Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    identifiers and counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    अधिकांश
    0.50
     продол
    0.44
     Handicap
    0.44
    িগণ
    0.43
     lanjut
    0.43
    糀
    0.43
     circulate
    0.42
     Printers
    0.42
     rupani
    0.42
     Convenient
    0.42
    POSITIVE LOGITS
    ال
    0.55
    س
    0.51
    ع
    0.44
    5
    0.42
    id
    0.42
    4
    0.42
    Version
    0.42
    Access
    0.41
    0.41
    ب
    0.41
    Act Density 0.008%

    No Known Activations